# Exploring the Hyperparameter Landscape of Adversarial Robustness

arXiv: https://arxiv.org/abs/1905.03837 · HTML: https://mlsanity.com/paper/1905.03837/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 May 2019.

## Built on by (most cited first, 4 of 4)

- [MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers](https://mlsanity.com/paper/2402.02263/) (2024)
- [Hyper-parameter Tuning for Adversarially Robust Models](https://mlsanity.com/paper/2304.02497/) (2023)
- [On the Noise Stability and Robustness of Adversarially Trained Networks on NVM Crossbars](https://mlsanity.com/paper/2109.09060/) (2021)
- [Survival of the Cheapest: Cost-Aware Hardware Adaptation for Adversarial Robustness](https://mlsanity.com/paper/2409.07609/) (2024)

## Abstract (arXiv)

Adversarial training shows promise as an approach for training models that are robust towards adversarial perturbation. In this paper, we explore some of the practical challenges of adversarial training. We present a sensitivity analysis that illustrates that the effectiveness of adversarial training hinges on the settings of a few salient hyperparameters. We show that the robustness surface that emerges across these salient parameters can be surprisingly complex and that therefore no effective one-size-fits-all parameter settings exist. We then demonstrate that we can use the same salient hyperparameters as tuning knob to navigate the tension that can arise between robustness and accuracy. Based on these findings, we present a practical approach that leverages hyperparameter optimization techniques for tuning adversarial training to maximize robustness while keeping the loss in accuracy within a defined budget.